| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.243478260869565, | |
| "eval_steps": 25, | |
| "global_step": 11, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2782608695652174, | |
| "grad_norm": 9.462660789489746, | |
| "learning_rate": 9.81771838126524e-05, | |
| "loss": 4.7356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2782608695652174, | |
| "eval_loss": 3.9605443477630615, | |
| "eval_runtime": 3.2569, | |
| "eval_samples_per_second": 15.352, | |
| "eval_steps_per_second": 3.992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5565217391304348, | |
| "grad_norm": 6.983944416046143, | |
| "learning_rate": 9.285640897740315e-05, | |
| "loss": 3.6661, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.8347826086956521, | |
| "grad_norm": 3.6327104568481445, | |
| "learning_rate": 8.446873302753784e-05, | |
| "loss": 2.8808, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.1739130434782608, | |
| "grad_norm": 13.186640739440918, | |
| "learning_rate": 7.369367558508489e-05, | |
| "loss": 4.8345, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.4521739130434783, | |
| "grad_norm": 7.955297946929932, | |
| "learning_rate": 6.140416772229784e-05, | |
| "loss": 2.3637, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.7304347826086957, | |
| "grad_norm": 4.790513038635254, | |
| "learning_rate": 4.859583227770218e-05, | |
| "loss": 2.4489, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.0695652173913044, | |
| "grad_norm": 4.571768760681152, | |
| "learning_rate": 3.630632441491512e-05, | |
| "loss": 3.4345, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.3478260869565215, | |
| "grad_norm": 2.352327346801758, | |
| "learning_rate": 2.5531266972462177e-05, | |
| "loss": 2.084, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.626086956521739, | |
| "grad_norm": 3.280284881591797, | |
| "learning_rate": 1.7143591022596845e-05, | |
| "loss": 1.8305, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.9043478260869566, | |
| "grad_norm": 4.499510288238525, | |
| "learning_rate": 1.1822816187347623e-05, | |
| "loss": 2.9147, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.243478260869565, | |
| "grad_norm": 3.5210437774658203, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2042, | |
| "step": 11 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 11, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.358385455782953e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |